Update README.md

README.md

@@ -12,9 +12,24 @@ pipeline_tag: text-generation
 tags:
 - chat
 ---
+# ChatBLOOM
 
 ChatBLOOM是基于[BLOOM](https://huggingface.co/bigscience/bloom-1b7)（17亿参数）训练的中英双语对话语言模型，此模型为SFT版本。
 详见[Github](https://github.com/NicholasCao/ChatBloom)。
 
 ChatBLOOM is a Chinese-English bilingual dialogue language model trained based on [BLOOM](https://huggingface.co/bigscience/bloom-1b7) (1.7 billion parameters). This model is the SFT version.
-See [Github](https://github.com/NicholasCao/ChatBloom) for details.
+See [Github](https://github.com/NicholasCao/ChatBloom) for details.
+
+## Usage
+```python
+tokenizer = AutoTokenizer.from_pretrained('nicholascao/chatbloom-1b7-sft')
+model = AutoModelForCausalLM.from_pretrained('nicholascao/chatbloom-1b7-sft')
+generation_config = GenerationConfig.from_pretrained('nicholascao/chatbloom-1b7-sft')
+
+inputs = tokenizer('<Human>: Hello <eoh> <Assistant>: ', return_tensors='pt').to(torch.cuda.current_device())
+model.to(torch.cuda.current_device())
+
+output = model.generate(**inputs, generation_config=generation_config)
+output = tokenizer.decode(output[0], skip_special_tokens=True)
+print(output)
+```